Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
package org.uma.jmetal.experiment;
import org.uma.jmetal.algorithm.Algorithm;
import org.uma.jmetal.algorithm.multiobjective.gde3.GDE3Builder;
import org.uma.jmetal.algorithm.multiobjective.mocell.MOCellBuilder;
import org.uma.jmetal.algorithm.multiobjective.nsgaii.NSGAIIBuilder;
import org.uma.jmetal.algorithm.multiobjective.smpso.SMPSOBuilder;
import org.uma.jmetal.algorithm.multiobjective.spea2.SPEA2Builder;
import org.uma.jmetal.operator.impl.crossover.DifferentialEvolutionCrossover;
import org.uma.jmetal.operator.impl.crossover.SBXCrossover;
import org.uma.jmetal.operator.impl.mutation.PolynomialMutation;
import org.uma.jmetal.operator.impl.selection.BinaryTournamentSelection;
import org.uma.jmetal.operator.impl.selection.DifferentialEvolutionSelection;
import org.uma.jmetal.problem.DoubleProblem;
import org.uma.jmetal.problem.Problem;
import org.uma.jmetal.problem.multiobjective.*;
import org.uma.jmetal.qualityindicator.impl.Epsilon;
import org.uma.jmetal.qualityindicator.impl.InvertedGenerationalDistancePlus;
import org.uma.jmetal.qualityindicator.impl.hypervolume.PISAHypervolume;
import org.uma.jmetal.solution.DoubleSolution;
import org.uma.jmetal.util.JMetalException;
import org.uma.jmetal.util.archive.impl.CrowdingDistanceArchive;
import org.uma.jmetal.util.evaluator.impl.SequentialSolutionListEvaluator;
import org.uma.jmetal.util.experiment.Experiment;
import org.uma.jmetal.util.experiment.ExperimentBuilder;
import org.uma.jmetal.util.experiment.component.*;
import org.uma.jmetal.util.experiment.util.ExperimentAlgorithm;
import org.uma.jmetal.util.experiment.util.ExperimentProblem;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
/**
* Example of experimental study based on solving the unconstrained problems included in jMetal.
*
* This experiment assumes that the reference Pareto front are known and that, given a problem named
* P, there is a corresponding file called P.pf containing its corresponding Pareto front. If this
* is not the case, please refer to class {@link DTLZStudy} to see an example of how to explicitly
* indicate the name of those files.
*
* Six quality indicators are used for performance assessment.
*
* The steps to carry out the experiment are:
* 1. Configure the experiment
* 2. Execute the algorithms
* 3. Generate the reference Pareto fronts
* 4. Compute the quality indicators
* 5. Generate Latex tables reporting means and medians
* 6. Generate Latex tables with the result of applying the Wilcoxon Rank Sum Test
* 7. Generate Latex tables with the ranking obtained by applying the Friedman test
* 8. Generate R scripts to obtain boxplots
*
* @author Antonio J. Nebro
*/
public class ConstraintProblemsStudy {
private static final int INDEPENDENT_RUNS = 25;
public static void main(String[] args) throws IOException {
if (args.length != 1) {
throw new JMetalException("Needed arguments: experimentBaseDirectory");
}
String experimentBaseDirectory = args[0];
List> problemList = new ArrayList<>();
problemList.add(new ExperimentProblem<>(new Binh2()));
problemList.add(new ExperimentProblem<>(new ConstrEx()));
problemList.add(new ExperimentProblem<>(new Golinski()));
problemList.add(new ExperimentProblem<>(new Srinivas()));
problemList.add(new ExperimentProblem<>(new Tanaka()));
problemList.add(new ExperimentProblem<>(new Water()));
List>> algorithmList =
configureAlgorithmList(problemList);
Experiment> experiment =
new ExperimentBuilder>("ConstrainedProblemsStudy")
.setAlgorithmList(algorithmList)
.setProblemList(problemList)
.setExperimentBaseDirectory(experimentBaseDirectory)
.setOutputParetoFrontFileName("FUN")
.setOutputParetoSetFileName("VAR")
.setReferenceFrontDirectory(experimentBaseDirectory + "/ConstrainedProblemsStudy/referenceFronts")
.setIndicatorList(Arrays.asList(
new Epsilon(),
new PISAHypervolume(),
new InvertedGenerationalDistancePlus()))
.setIndependentRuns(INDEPENDENT_RUNS)
.setNumberOfCores(8)
.build();
new ExecuteAlgorithms<>(experiment).run();
new GenerateReferenceParetoSetAndFrontFromDoubleSolutions(experiment).run();
new ComputeQualityIndicators<>(experiment).run();
new GenerateLatexTablesWithStatistics(experiment).run();
new GenerateWilcoxonTestTablesWithR<>(experiment).run();
new GenerateFriedmanTestTables<>(experiment).run();
new GenerateBoxplotsWithR<>(experiment).setRows(3).setColumns(3).run();
}
/**
* The algorithm list is composed of pairs {@link Algorithm} + {@link Problem} which form part of
* a {@link ExperimentAlgorithm}, which is a decorator for class {@link Algorithm}. The {@link
* ExperimentAlgorithm} has an optional tag component, that can be set as it is shown in this example,
* where four variants of a same algorithm are defined.
*/
static List>> configureAlgorithmList(
List> problemList) {
List>> algorithms = new ArrayList<>();
for (int run = 0; run < INDEPENDENT_RUNS; run++) {
for (int i = 0; i < problemList.size(); i++) {
Algorithm> algorithm = new NSGAIIBuilder<>(
problemList.get(i).getProblem(),
new SBXCrossover(1.0, 20),
new PolynomialMutation(1.0 / problemList.get(i).getProblem().getNumberOfVariables(), 20.0))
.setMaxEvaluations(25000)
.setPopulationSize(100)
.build();
algorithms.add(new ExperimentAlgorithm<>(algorithm, problemList.get(i),run));
}
for (int i = 0; i < problemList.size(); i++) {
Algorithm> algorithm = new SPEA2Builder(
problemList.get(i).getProblem(),
new SBXCrossover(1.0, 10.0),
new PolynomialMutation(1.0 / problemList.get(i).getProblem().getNumberOfVariables(), 20.0))
.build();
algorithms.add(new ExperimentAlgorithm<>(algorithm, problemList.get(i), run));
}
for (int i = 0; i < problemList.size(); i++) {
double mutationProbability = 1.0 / problemList.get(i).getProblem().getNumberOfVariables();
double mutationDistributionIndex = 20.0;
Algorithm> algorithm = new SMPSOBuilder((DoubleProblem) problemList.get(i).getProblem(),
new CrowdingDistanceArchive(100))
.setMutation(new PolynomialMutation(mutationProbability, mutationDistributionIndex))
.setMaxIterations(250)
.setSwarmSize(100)
.setSolutionListEvaluator(new SequentialSolutionListEvaluator())
.build();
algorithms.add(new ExperimentAlgorithm<>(algorithm, problemList.get(i), run));
}
for (int i = 0; i < problemList.size(); i++) {
double cr = 0.5;
double f = 0.5;
Algorithm> algorithm = new GDE3Builder((DoubleProblem) problemList.get(i).getProblem())
.setCrossover(new DifferentialEvolutionCrossover(cr, f, "rand/1/bin"))
.setSelection(new DifferentialEvolutionSelection())
.setMaxEvaluations(25000)
.setPopulationSize(100)
.setSolutionSetEvaluator(new SequentialSolutionListEvaluator<>())
.build();
algorithms.add(new ExperimentAlgorithm<>(algorithm, problemList.get(i), run));
}
for (int i = 0; i < problemList.size(); i++) {
Algorithm> algorithm = new MOCellBuilder(
(DoubleProblem) problemList.get(i).getProblem(),
new SBXCrossover(1.0, 20.0),
new PolynomialMutation(1.0 / problemList.get(i).getProblem().getNumberOfVariables(), 20.0))
.setSelectionOperator(new BinaryTournamentSelection<>())
.setMaxEvaluations(25000)
.setPopulationSize(100)
.setArchive(new CrowdingDistanceArchive(100))
.build();
algorithms.add(new ExperimentAlgorithm<>(algorithm, problemList.get(i), run));
}
}
return algorithms;
}
}
